Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
arXiv:1512.00172
Abstract
Fisher Vector classifiers and Deep Neural Networks (DNNs) are popular and successful algorithms for solving image classification problems. However, both are generally considered `black box' predictors as the non-linear transformations involved have so far prevented transparent and interpretable reasoning. Recently, a principled technique, Layer-wise Relevance Propagation (LRP), has been developed in order to better comprehend the inherent structured reasoning of complex nonlinear classification models such as Bag of Feature models or DNNs. In this paper we (1) extend the LRP framework also for Fisher Vector classifiers and then use it as analysis tool to (2) quantify the importance of context for classification, (3) qualitatively compare DNNs against FV classifiers in terms of important image regions and (4) detect potential flaws and biases in data. All experiments are performed on the PASCAL VOC 2007 data set.
17 pages (10 main document + references , 7 appendix) 1 Table 7 Figures 1 Algorithm submitted to CVPR on 06/11/2025
References in corpus (6)
- Sequence to Sequence Learning with Neural Networks
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Going Deeper with Convolutions
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
- Understanding Deep Image Representations by Inverting Them
- Evaluating the visualization of what a Deep Neural Network has learned